no code implementations • 14 Apr 2024 • Rachmad Vidya Wicaksana Putra, Alberto Marchisio, Muhammad Shafique
The experimental results show that our proposed framework can maintain high accuracy (i. e., 84. 12% accuracy) with 68. 75% memory saving, 3. 58x speed-up, and 4. 03x energy efficiency improvement as compared to the state-of-the-art work for NCARS dataset, thereby enabling energy-efficient embodied SNN deployments for autonomous agents.
no code implementations • 4 Apr 2024 • Rachmad Vidya Wicaksana Putra, Alberto Marchisio, Fakhreddine Zayer, Jorge Dias, Muhammad Shafique
Toward this, recent advances in neuromorphic computing with Spiking Neural Networks (SNN) have demonstrated the potential to enable the embodied intelligence for robotics through bio-plausible computing paradigm that mimics how the biological brain works, known as "neuromorphic artificial intelligence (AI)".
no code implementations • 4 Apr 2024 • Iqra Bano, Rachmad Vidya Wicaksana Putra, Alberto Marchisio, Muhammad Shafique
Toward this, we propose a novel methodology to systematically study and analyze the impact of SNN parameters considering event-based automotive data, then leverage this analysis for enhancing SNN developments.
no code implementations • 3 Apr 2024 • Nouhaila Innan, Alberto Marchisio, Muhammad Shafique, Mohamed Bennai
This study introduces the Quantum Federated Neural Network for Financial Fraud Detection (QFNN-FFD), a cutting-edge framework merging Quantum Machine Learning (QML) and quantum computing with Federated Learning (FL) for financial fraud detection.
no code implementations • 2 Apr 2024 • Rachmad Vidya Wicaksana Putra, Muhammad Shafique
Spiking Neural Networks (SNNs) can offer ultra low power/ energy consumption for machine learning-based applications due to their sparse spike-based operations.
no code implementations • 29 Mar 2024 • Maha Nawaz, Abdul Basit, Muhammad Shafique
This demonstrates that our MindArm provides a novel approach for an alternate low-cost mind-controlled prosthetic devices for all patients.
no code implementations • 18 Mar 2024 • Amira Guesmi, Muhammad Abdullah Hanif, Ihsen Alouani, Bassem Ouni, Muhammad Shafique
In this paper, we introduce SSAP (Shape-Sensitive Adversarial Patch), a novel approach designed to comprehensively disrupt monocular depth estimation (MDE) in autonomous navigation applications.
no code implementations • 16 Mar 2024 • Nouhaila Innan, Muhammad Al-Zafar Khan, Alberto Marchisio, Muhammad Shafique, Mohamed Bennai
In this study, we explore the innovative domain of Quantum Federated Learning (QFL) as a framework for training Quantum Machine Learning (QML) models via distributed networks.
no code implementations • 8 Mar 2024 • Erik Ostrowski, Muhammad Shafique
In this paper, we propose our architecture that takes advantage of the fact that in hardware-limited environments, we often refrain from using the highest available input resolutions to guarantee a higher throughput.
no code implementations • 28 Feb 2024 • Abdul Basit, Khizar Hussain, Muhammad Abdullah Hanif, Muhammad Shafique
MedAide achieves 77\% accuracy in medical consultations and scores 56 in USMLE benchmark, enabling an energy-efficient healthcare assistance platform that alleviates privacy concerns due to edge-based deployment, thereby empowering the community.
no code implementations • 23 Feb 2024 • Abolfazl Younesi, Mohsen Ansari, Mohammadamin Fazli, Alireza Ejlali, Muhammad Shafique, Jörg Henkel
In today's digital age, Convolutional Neural Networks (CNNs), a subset of Deep Learning (DL), are widely used for various computer vision tasks such as image classification, object detection, and image segmentation.
no code implementations • 17 Feb 2024 • Rachmad Vidya Wicaksana Putra, Muhammad Shafique
Autonomous mobile agents (e. g., UAVs and UGVs) are typically expected to incur low power/energy consumption for solving machine learning tasks (such as object recognition), as these mobile agents are usually powered by portable batteries.
no code implementations • 15 Feb 2024 • Eugenio Ressa, Alberto Marchisio, Maurizio Martina, Guido Masera, Muhammad Shafique
Towards this, we design a hardware architecture, TinyCL, to perform CL on resource-constrained autonomous systems.
no code implementations • 14 Feb 2024 • Muhammad Kashif, Muhammad Shafique
To resolve this, we propose a novel architecture, Residual Quanvolutional Neural Networks (ResQuNNs), leveraging the concept of residual learning, which facilitates the flow of gradients by adding skip connections between layers.
no code implementations • 9 Feb 2024 • Nandish Chattopadhyay, Amira Guesmi, Muhammad Shafique
Adversarial patch attacks pose a significant threat to the practical deployment of deep learning systems.
no code implementations • 20 Nov 2023 • Nandish Chattopadhyay, Amira Guesmi, Muhammad Abdullah Hanif, Bassem Ouni, Muhammad Shafique
ODDR employs a three-stage pipeline: Fragmentation, Segregation, and Neutralization, providing a model-agnostic solution applicable to both image classification and object detection tasks.
no code implementations • 20 Nov 2023 • Abdul Rahoof, Vivek Chaturvedi, Mahesh Raveendranatha Panicker, Muhammad Shafique
Accelerating compute intensive non-real-time beam-forming algorithms in ultrasound imaging using deep learning architectures has been gaining momentum in the recent past.
no code implementations • 16 Oct 2023 • Kamila Zaman, Alberto Marchisio, Muhammad Abdullah Hanif, Muhammad Shafique
Quantum Computing (QC) claims to improve the efficiency of solving complex problems, compared to classical computing.
no code implementations • 10 Aug 2023 • Farzad Nikfam, Raffaele Casaburi, Alberto Marchisio, Maurizio Martina, Muhammad Shafique
Machine learning (ML) is widely used today, especially through deep neural networks (DNNs), however, increasing computational load and resource requirements have led to cloud-based solutions.
no code implementations • 6 Aug 2023 • Amira Guesmi, Muhammad Abdullah Hanif, Bassem Ouni, Muhammad Shafique
In this paper, we investigate the vulnerability of MDE to adversarial patches.
no code implementations • 20 Jul 2023 • Vasileios Leon, Muhammad Abdullah Hanif, Giorgos Armeniakos, Xun Jiao, Muhammad Shafique, Kiamal Pekmestzi, Dimitrios Soudris
The challenging deployment of compute-intensive applications from domains such Artificial Intelligence (AI) and Digital Signal Processing (DSP), forces the community of computing systems to explore new design approaches.
1 code implementation • 29 Jun 2023 • Mahum Naseer, Osman Hasan, Muhammad Shafique
This in turn allows the analysis of NN safety properties using the new framework, in addition to all the NN properties already included with FANNet.
no code implementations • 21 May 2023 • Muhammad Abdullah Hanif, Muhammad Shafique
To address this issue, we propose a novel Fault-Aware Quantization (FAQ) technique for mitigating the effects of stuck-at permanent faults in the on-chip weight memory of DNN accelerators at a negligible overhead cost compared to fault-aware retraining while offering comparable accuracy results.
no code implementations • 19 May 2023 • Amira Guesmi, Ruitian Ding, Muhammad Abdullah Hanif, Ihsen Alouani, Muhammad Shafique
Patch-based adversarial attacks were proven to compromise the robustness and reliability of computer vision systems.
2 code implementations • 25 Apr 2023 • Sizhuo Liu, Muhammad Shafique, Philip Schniter, Rizwan Ahmad
However, unlike traditional PnP approaches that utilize generic denoisers or train application-specific denoisers using high-quality images or image patches, ReSiDe directly trains the denoiser on the image or images that are being reconstructed from the undersampled data.
no code implementations • 20 Apr 2023 • Muhammad Abdullah Hanif, Muhammad Shafique
To realize these concepts, in this work, we present a novel framework, eFAT, that computes the resilience of a given DNN to faults at different fault rates and with different levels of retraining, and it uses that knowledge to build a resilience map given a user-defined accuracy constraint.
no code implementations • 8 Apr 2023 • Alberto Marchisio, Antonio De Marco, Alessio Colucci, Maurizio Martina, Muhammad Shafique
Overall, CapsNets achieve better robustness against adversarial examples and affine transformations, compared to a traditional CNN with a similar number of parameters.
1 code implementation • 8 Apr 2023 • Alberto Marchisio, Davide Dura, Maurizio Capra, Maurizio Martina, Guido Masera, Muhammad Shafique
In particular, fixed-point quantization is desirable to ease the computations using lightweight blocks, like adders and multipliers, of the underlying hardware.
no code implementations • 8 Apr 2023 • Rachmad Vidya Wicaksana Putra, Muhammad Abdullah Hanif, Muhammad Shafique
The key mechanisms of our EnforceSNN are: (1) employing quantized weights to reduce the DRAM access energy; (2) devising an efficient DRAM mapping policy to minimize the DRAM energy-per-access; (3) analyzing the SNN error tolerance to understand its accuracy profile considering different bit error rate (BER) values; (4) leveraging the information for developing an efficient fault-aware training (FAT) that considers different BER values and bit error locations in DRAM to improve the SNN error tolerance; and (5) developing an algorithm to select the SNN model that offers good trade-offs among accuracy, memory, and energy consumption.
no code implementations • 8 Apr 2023 • Rachmad Vidya Wicaksana Putra, Muhammad Abdullah Hanif, Muhammad Shafique
Our FAM technique leverages the fault map of SNN compute engine for (i) minimizing weight corruption when mapping weight bits on the faulty memory cells, and (ii) selectively employing faulty neurons that do not cause significant accuracy degradation to maintain accuracy and throughput, while considering the SNN operations and processing dataflow.
no code implementations • 29 Mar 2023 • Mahum Naseer, Muhammad Shafique
Owing to their remarkable learning (and relearning) capabilities, deep neural networks (DNNs) find use in numerous real-world applications.
no code implementations • 24 Mar 2023 • Wenqing Li, Yue Wang, Muhammad Shafique, Saif Eddin Jabari
Recent studies reveal that Autonomous Vehicles (AVs) can be manipulated by hidden backdoors, causing them to perform harmful actions when activated by physical triggers.
1 code implementation • 14 Mar 2023 • Erik Ostrowski, Muhammad Shafique
One key bottleneck of employing state-of-the-art semantic segmentation networks in the real world is the availability of training labels.
1 code implementation • 14 Mar 2023 • Bharath Srinivas Prabakaran, Paul Hamelmann, Erik Ostrowski, Muhammad Shafique
Ultrasound imaging is one of the most prominent technologies to evaluate the growth, progression, and overall health of a fetus during its gestation.
2 code implementations • 14 Mar 2023 • Bharath Srinivas Prabakaran, Erik Ostrowski, Muhammad Shafique
Weakly Supervised Semantic Segmentation (WSSS) relying only on image-level supervision is a promising approach to deal with the need for Segmentation networks, especially for generating a large number of pixel-wise masks in a given dataset.
2 code implementations • 14 Mar 2023 • Erik Ostrowski, Bharath Srinivas Prabakaran, Muhammad Shafique
Our new PerimeterFit module will be applied to pre-refine the CAM predictions before using the pixel-similarity-based network.
1 code implementation • 14 Mar 2023 • Erik Ostrowski, Bharath Srinivas Prabakaran, Muhammad Shafique
Reliable classification and detection of certain medical conditions, in images, with state-of-the-art semantic segmentation networks, require vast amounts of pixel-wise annotation.
no code implementations • 14 Mar 2023 • Alessio Colucci, Andreas Steininger, Muhammad Shafique
Using importance sampling in FAT reduces the overhead required for finding faults that lead to a predetermined drop in accuracy by more than 12x.
no code implementations • 3 Mar 2023 • Rachmad Vidya Wicaksana Putra, Muhammad Shafique
These requirements can be fulfilled by Spiking Neural Networks (SNNs) as they offer low power/energy processing due to their sparse computations and efficient online learning with bio-inspired learning mechanisms for adapting to different environments.
no code implementations • 3 Mar 2023 • Amira Guesmi, Ioan Marius Bilasco, Muhammad Shafique, Ihsen Alouani
Physical adversarial attacks pose a significant practical threat as it deceives deep learning systems operating in the real world by producing prominent and maliciously designed physical perturbations.
no code implementations • 3 Mar 2023 • Ayoub Arous, Amira Guesmi, Muhammad Abdullah Hanif, Ihsen Alouani, Muhammad Shafique
Towards investigating new ground for better privacy-utility trade-off, this work questions; (i) if models' hyperparameters have any inherent impact on ML models' privacy-preserving properties, and (ii) if models' hyperparameters have any impact on the privacy/utility trade-off of differentially private models.
no code implementations • 2 Mar 2023 • Amira Guesmi, Muhammad Abdullah Hanif, Ihsen Alouani, Muhammad Shafique
APARATE, results in a mean depth estimation error surpassing $0. 5$, significantly impacting as much as $99\%$ of the targeted region when applied to CNN-based MDE models.
no code implementations • 2 Mar 2023 • Amira Guesmi, Muhammad Abdullah Hanif, Muhammad Shafique
Unlike mask based fake-weather attacks that require access to the underlying computing hardware or image memory, our attack is based on emulating the effects of a natural weather condition (i. e., Raindrops) that can be printed on a translucent sticker, which is externally placed over the lens of a camera.
1 code implementation • 24 Feb 2023 • Mahum Naseer, Bharath Srinivas Prabakaran, Osman Hasan, Muhammad Shafique
In contrast, UnbiasedNets provides a notable improvement over existing works, while even reducing the robustness bias significantly in some cases, as observed by comparing the NNs trained on the diversified and original datasets.
no code implementations • 24 Dec 2022 • Rachmad Vidya Wicaksana Putra, Muhammad Shafique
Towards this, we propose a Mantis methodology to systematically employ SNNs on autonomous mobile agents to enable energy-efficient processing and adaptive capabilities in dynamic environments.
no code implementations • 29 Nov 2022 • Christopher J. Holder, Majid Khonji, Jorge Dias, Muhammad Shafique
A major challenge in machine learning is resilience to out-of-distribution data, that is data that exists outside of the distribution of a model's training data.
no code implementations • 9 Nov 2022 • Christopher J. Holder, Muhammad Shafique
Global localisation from visual data is a challenging problem applicable to many robotics domains.
1 code implementation • 13 Oct 2022 • Farzad Nikfam, Alberto Marchisio, Maurizio Martina, Muhammad Shafique
The experiments show comparable results with the related works, and in several experiments, the adversarial training of DNNs using our AccelAT framework is conducted up to 2 times faster than the existing techniques.
1 code implementation • 11 Oct 2022 • Alberto Marchisio, Vojtech Mrazek, Andrea Massa, Beatrice Bussolino, Maurizio Martina, Muhammad Shafique
Neural Architecture Search (NAS) algorithms aim at finding efficient Deep Neural Network (DNN) architectures for a given application under given system constraints.
no code implementations • 3 Aug 2022 • Alberto Viale, Alberto Marchisio, Maurizio Martina, Guido Masera, Muhammad Shafique
Autonomous Driving (AD) related features represent important elements for the next generation of mobile robots and autonomous vehicles focused on increasingly intelligent, autonomous, and interconnected systems.
no code implementations • 31 Jul 2022 • Muhammad Abdullah Hanif, Giuseppe Maria Sarda, Alberto Marchisio, Guido Masera, Maurizio Martina, Muhammad Shafique
The high computational complexity of these networks, which translates to increased energy consumption, is the foremost obstacle towards deploying large DNNs in resource-constrained systems.
no code implementations • 31 Jul 2022 • Alessio Colucci, Andreas Steininger, Muhammad Shafique
Towards better reliability analysis for DNNs, we present enpheeph, a Fault Injection Framework for Spiking and Compressed DNNs.
no code implementations • 21 Jun 2022 • Alberto Marchisio, Beatrice Bussolino, Edoardo Salvati, Maurizio Martina, Guido Masera, Muhammad Shafique
In our experiments, we evaluate tradeoffs between area, power consumption, and critical path delay of the designs implemented with the ASIC design flow, and the accuracy of the quantized CapsNets, compared to the exact functions.
no code implementations • 17 Jun 2022 • Rachmad Vidya Wicaksana Putra, Muhammad Shafique
Larger Spiking Neural Network (SNN) models are typically favorable as they can offer higher accuracy.
no code implementations • 17 Jun 2022 • Christopher J. Holder, Muhammad Shafique
Semantic segmentation is the problem of assigning a class label to every pixel in an image, and is an important component of an autonomous vehicle vision stack for facilitating scene understanding and object detection.
2 code implementations • 1 Jun 2022 • Mahya Morid Ahmadi, Lilas Alrahis, Alessio Colucci, Ozgur Sinanoglu, Muhammad Shafique
We release the NeuroUnlock and the ReDLock as open-source frameworks.
no code implementations • 27 May 2022 • Alberto Marchisio, Giovanni Caramia, Maurizio Martina, Muhammad Shafique
Recently, Deep Neural Networks (DNNs) have achieved remarkable performances in many applications, while several studies have enhanced their vulnerabilities to malicious attacks.
no code implementations • 24 May 2022 • Rachmad Vidya Wicaksana Putra, Muhammad Shafique
Our lpSpikeCon methodology employs the following key steps: (1) analyzing the impacts of training the SNN model under unsupervised continual learning settings with reduced weight precision on the inference accuracy; (2) leveraging this study to identify SNN parameters that have a significant impact on the inference accuracy; and (3) developing an algorithm for searching the respective SNN parameter values that improve the quality of unsupervised continual learning.
no code implementations • 18 Apr 2022 • Shail Dave, Alberto Marchisio, Muhammad Abdullah Hanif, Amira Guesmi, Aviral Shrivastava, Ihsen Alouani, Muhammad Shafique
The real-world use cases of Machine Learning (ML) have exploded over the past few years.
no code implementations • 17 Mar 2022 • Yue Wang, Wenqing Li, Esha Sarkar, Muhammad Shafique, Michail Maniatakos, Saif Eddin Jabari
Based on our theoretical analysis and experimental results, we demonstrate the effectiveness of PiDAn in defending against backdoor attacks that use different settings of poisoned samples on GTSRB and ILSVRC2012 datasets.
no code implementations • 10 Mar 2022 • Rachmad Vidya Wicaksana Putra, Muhammad Abdullah Hanif, Muhammad Shafique
These errors can change the weight values and neuron operations in the compute engine of SNN accelerators, thereby leading to incorrect outputs and accuracy degradation.
no code implementations • 20 Sep 2021 • Muhammad Shafique, Alberto Marchisio, Rachmad Vidya Wicaksana Putra, Muhammad Abdullah Hanif
Afterward, we discuss how to further improve the performance (latency) and the energy efficiency of Edge AI systems through HW/SW-level optimizations, such as pruning, quantization, and approximation.
no code implementations • 7 Sep 2021 • Bharath Srinivas Prabakaran, Asima Akhtar, Semeen Rehman, Osman Hasan, Muhammad Shafique
We are successful in identifying Pareto-optimal designs, which can reduce the storage overhead of the DNN by ~30MB for a quality loss of less than 0. 5%.
1 code implementation • 1 Sep 2021 • Alberto Marchisio, Giacomo Pira, Maurizio Martina, Guido Masera, Muhammad Shafique
Spiking Neural Networks (SNNs) aim at providing energy-efficient learning capabilities when implemented on neuromorphic chips with event-based Dynamic Vision Sensors (DVS).
no code implementations • 23 Aug 2021 • Rachmad Vidya Wicaksana Putra, Muhammad Abdullah Hanif, Muhammad Shafique
Since recent works still focus on the fault-modeling and random fault injection in SNNs, the impact of memory faults in SNN hardware architectures on accuracy and the respective fault-mitigation techniques are not thoroughly explored.
no code implementations • 5 Jul 2021 • Rachmad Vidya Wicaksana Putra, Muhammad Shafique
A prominent technique for reducing the memory footprint of Spiking Neural Networks (SNNs) without decreasing the accuracy significantly is quantization.
1 code implementation • 1 Jul 2021 • Alberto Viale, Alberto Marchisio, Maurizio Martina, Guido Masera, Muhammad Shafique
Our best experiment achieves an accuracy on offline implementation of 86%, that drops to 83% when it is ported onto the Loihi Chip.
1 code implementation • 1 Jul 2021 • Alberto Marchisio, Giacomo Pira, Maurizio Martina, Guido Masera, Muhammad Shafique
Spiking Neural Networks (SNNs), despite being energy-efficient when implemented on neuromorphic hardware and coupled with event-based Dynamic Vision Sensors (DVS), are vulnerable to security threats, such as adversarial attacks, i. e., small perturbations added to the input for inducing a misclassification.
no code implementations • 26 May 2021 • Khadija Shaheen, Muhammad Abdullah Hanif, Osman Hasan, Muhammad Shafique
Continual learning is essential for all real-world applications, as frozen pre-trained models cannot effectively deal with non-stationary data distributions.
no code implementations • 5 May 2021 • Faiq Khalid, Muhammad Abdullah Hanif, Muhammad Shafique
From tiny pacemaker chips to aircraft collision avoidance systems, the state-of-the-art Cyber-Physical Systems (CPS) have increasingly started to rely on Deep Neural Networks (DNNs).
no code implementations • 28 Feb 2021 • Rachmad Vidya Wicaksana Putra, Muhammad Abdullah Hanif, Muhammad Shafique
The key mechanisms of SparkXD are: (1) improving the SNN error tolerance through fault-aware training that considers bit errors from approximate DRAM, (2) analyzing the error tolerance of the improved SNN model to find the maximum tolerable bit error rate (BER) that meets the targeted accuracy constraint, and (3) energy-efficient DRAM data mapping for the resilient SNN model that maps the weights in the appropriate DRAM location to minimize the DRAM access energy.
no code implementations • 28 Feb 2021 • Rachmad Vidya Wicaksana Putra, Muhammad Shafique
Spiking Neural Networks (SNNs) bear the potential of efficient unsupervised and continual learning capabilities because of their biological plausibility, but their complexity still poses a serious research challenge to enable their energy-efficient design for resource-constrained scenarios (like embedded systems, IoT-Edge, etc.).
no code implementations • 29 Jan 2021 • Muhammad Abdullah Hanif, Muhammad Shafique
We propose DNN-Life, a specialized aging analysis and mitigation framework for DNNs, which jointly exploits hardware- and software-level knowledge to improve the lifetime of a DNN weight memory with reduced energy overhead.
Quantization Hardware Architecture
no code implementations • 4 Jan 2021 • Muhammad Shafique, Mahum Naseer, Theocharis Theocharides, Christos Kyrkou, Onur Mutlu, Lois Orosa, Jungwook Choi
Machine Learning (ML) techniques have been rapidly adopted by smart Cyber-Physical Systems (CPS) and Internet-of-Things (IoT) due to their powerful decision-making capabilities.
no code implementations • 21 Dec 2020 • Maurizio Capra, Beatrice Bussolino, Alberto Marchisio, Guido Masera, Maurizio Martina, Muhammad Shafique
Currently, Machine Learning (ML) is becoming ubiquitous in everyday life.
1 code implementation • 9 Dec 2020 • Rida El-Allami, Alberto Marchisio, Muhammad Shafique, Ihsen Alouani
We thoroughly study SNNs security under different adversarial attacks in the strong white-box setting, with different noise budgets and under variable spiking parameters.
no code implementations • 9 Dec 2020 • Alessio Colucci, Dávid Juhász, Martin Mosbeck, Alberto Marchisio, Semeen Rehman, Manfred Kreutzer, Guenther Nadbath, Axel Jantsch, Muhammad Shafique
Training of the policy is supported by Machine Learning-based analytical models for quick performance estimation, thereby drastically reducing the time spent for dynamic profiling.
no code implementations • 21 Nov 2020 • Faiq Khalid, Syed Rafay Hasan, Sara Zia, Osman Hasan, Falah Awwad, Muhammad Shafique
To reduce the overhead of data acquisition, we propose a single power-port current acquisition block using current sensors in time-division multiplexing, which increases accuracy while incurring reduced area overhead.
no code implementations • 12 Oct 2020 • Alberto Marchisio, Vojtech Mrazek, Muhammad Abdullah Hanif, Muhammad Shafique
We analyze the corresponding on-chip memory requirements and leverage it to propose a novel methodology to explore different scratchpad memory designs and their energy/area trade-offs.
1 code implementation • 19 Aug 2020 • Alberto Marchisio, Andrea Massa, Vojtech Mrazek, Beatrice Bussolino, Maurizio Martina, Muhammad Shafique
Deep Neural Networks (DNNs) have made significant improvements to reach the desired accuracy to be employed in a wide variety of Machine Learning (ML) applications.
no code implementations • 17 Jul 2020 • Rachmad Vidya Wicaksana Putra, Muhammad Shafique
FSpiNN reduces the computational requirements by reducing the number of neuronal operations, the STDP-based synaptic weight updates, and the STDP complexity.
1 code implementation • 16 May 2020 • Riccardo Massa, Alberto Marchisio, Maurizio Martina, Muhammad Shafique
Towards the conversion from a DNN to an SNN, we perform a comprehensive analysis of such process, specifically designed for Intel Loihi, showing our methodology for the design of an SNN that achieves nearly the same accuracy results as its corresponding DNN.
no code implementations • 16 May 2020 • Valerio Venceslai, Alberto Marchisio, Ihsen Alouani, Maurizio Martina, Muhammad Shafique
Due to their proven efficiency, machine-learning systems are deployed in a wide range of complex real-life problems.
no code implementations • 21 Apr 2020 • Rachmad Vidya Wicaksana Putra, Muhammad Abdullah Hanif, Muhammad Shafique
Many convolutional neural network (CNN) accelerators face performance- and energy-efficiency challenges which are crucial for embedded implementations, due to high DRAM access latency and energy.
no code implementations • 15 Apr 2020 • Alberto Marchisio, Beatrice Bussolino, Alessio Colucci, Maurizio Martina, Guido Masera, Muhammad Shafique
Capsule Networks (CapsNets), recently proposed by the Google Brain team, have superior learning capabilities in machine learning tasks, like image classification, compared to the traditional CNNs.
no code implementations • 3 Dec 2019 • Mahum Naseer, Mishal Fatima Minhas, Faiq Khalid, Muhammad Abdullah Hanif, Osman Hasan, Muhammad Shafique
With a constant improvement in the network architectures and training methodologies, Neural Networks (NNs) are increasingly being deployed in real-world Machine Learning systems.
no code implementations • 2 Dec 2019 • Le-Ha Hoang, Muhammad Abdullah Hanif, Muhammad Shafique
In this paper, we perform a comprehensive error resilience analysis of DNNs subjected to hardware faults (e. g., permanent faults) in the weight memory.
no code implementations • 2 Dec 2019 • Alberto Marchisio, Vojtech Mrazek, Muhammad Abudllah Hanif, Muhammad Shafique
To the best of our knowledge, this is the first proof-of-concept for employing approximations on the specialized CapsNet hardware.
1 code implementation • 11 Jun 2019 • Vojtech Mrazek, Zdenek Vasicek, Lukas Sekanina, Muhammad Abdullah Hanif, Muhammad Shafique
A suitable approximate multiplier is then selected for each computing element from a library of approximate multipliers in such a way that (i) one approximate multiplier serves several layers, and (ii) the overall classification error and energy consumption are minimized.
1 code implementation • 24 May 2019 • Alberto Marchisio, Beatrice Bussolino, Alessio Colucci, Muhammad Abdullah Hanif, Maurizio Martina, Guido Masera, Muhammad Shafique
The goal is to reduce the hardware requirements of CapsNets by removing unused/redundant connections and capsules, while keeping high accuracy through tests of different learning rate policies and batch sizes.
2 code implementations • 22 Feb 2019 • Vojtech Mrazek, Muhammad Abdullah Hanif, Zdenek Vasicek, Lukas Sekanina, Muhammad Shafique
Because these libraries contain from tens to thousands of approximate implementations for a single arithmetic operation it is intractable to find an optimal combination of approximate circuits in the library even for an application consisting of a few operations.
no code implementations • 4 Feb 2019 • Alberto Marchisio, Giorgio Nanfa, Faiq Khalid, Muhammad Abdullah Hanif, Maurizio Martina, Muhammad Shafique
We perform an in-depth evaluation for a Spiking Deep Belief Network (SDBN) and a DNN having the same number of layers and neurons (to obtain a fair comparison), in order to study the efficiency of our methodology and to understand the differences between SNNs and DNNs w. r. t.
no code implementations • 4 Feb 2019 • Rachmad Vidya Wicaksana Putra, Muhammad Abdullah Hanif, Muhammad Shafique
Our experimental results show that the ROMANet saves DRAM access energy by 12% for the AlexNet, by 36% for the VGG-16, and by 46% for the MobileNet, while also improving the DRAM throughput by 10%, as compared to the state-of-the-art.
no code implementations • 4 Feb 2019 • Alberto Marchisio, Muhammad Abdullah Hanif, Mohammad Taghi Teimoori, Muhammad Shafique
By leveraging this analysis, we propose a methodology to explore different on-chip memory designs and a power-gating technique to further reduce the energy consumption, depending upon the utilization across different operations of a CapsuleNet.
1 code implementation • 29 Jan 2019 • Faiq Khalid, Hassan Ali, Muhammad Abdullah Hanif, Semeen Rehman, Rehan Ahmed, Muhammad Shafique
To address this limitation, decision-based attacks have been proposed which can estimate the model but they require several thousand queries to generate a single untargeted attack image.
no code implementations • 28 Jan 2019 • Alberto Marchisio, Giorgio Nanfa, Faiq Khalid, Muhammad Abdullah Hanif, Maurizio Martina, Muhammad Shafique
Capsule Networks preserve the hierarchical spatial relationships between objects, and thereby bears a potential to surpass the performance of traditional Convolutional Neural Networks (CNNs) in performing tasks like image classification.
no code implementations • 5 Nov 2018 • Faiq Khalid, Muhammad Abdullah Hanif, Semeen Rehman, Muhammad Shafique
Therefore, computing paradigms are evolving towards machine learning (ML)-based systems because of their ability to efficiently and accurately process the enormous amount of data.
no code implementations • 4 Nov 2018 • Faiq Khalid, Syed Rafay Hasan, Osman Hasan, Muhammad Shafique
We present a run-time methodology for HT detection that employs a multi-parameter statistical traffic modeling of the communication channel in a given System-on-Chip (SoC), named as SIMCom.
no code implementations • 4 Nov 2018 • Faiq Khalid, Muhammmad Abdullah Hanif, Semeen Rehman, Junaid Qadir, Muhammad Shafique
Deep neural networks (DNN)-based machine learning (ML) algorithms have recently emerged as the leading ML paradigm particularly for the task of classification due to their superior capability of learning efficiently from large datasets.
1 code implementation • 4 Nov 2018 • Hassan Ali, Faiq Khalid, Hammad Tariq, Muhammad Abdullah Hanif, Semeen Rehman, Rehan Ahmed, Muhammad Shafique
In this paper, we introduce a novel technique based on the Secure Selective Convolutional (SSC) techniques in the training loop that increases the robustness of a given DNN by allowing it to learn the data distribution based on the important edges in the input image.
1 code implementation • 4 Nov 2018 • Faiq Khalid, Hassan Ali, Hammad Tariq, Muhammad Abdullah Hanif, Semeen Rehman, Rehan Ahmed, Muhammad Shafique
Adversarial examples have emerged as a significant threat to machine learning algorithms, especially to the convolutional neural networks (CNNs).
no code implementations • 2 Nov 2018 • Alberto Marchisio, Muhammad Abdullah Hanif, Muhammad Shafique
In this paper, we propose CapsAcc, the first specialized CMOS-based hardware architecture to perform CapsuleNets inference with high performance and energy efficiency.
Distributed, Parallel, and Cluster Computing Hardware Architecture
no code implementations • 2 Nov 2018 • Faiq Khalid, Muhammad Abdullah Hanif, Semeen Rehman, Rehan Ahmed, Muhammad Shafique
Most of the data manipulation attacks on deep neural networks (DNNs) during the training stage introduce a perceptible noise that can be catered by preprocessing during inference or can be identified during the validation phase.
no code implementations • 30 Oct 2018 • Muhammad Abdullah Hanif, Rachmad Vidya Wicaksana Putra, Muhammad Tanvir, Rehan Hafiz, Semeen Rehman, Muhammad Shafique
The state-of-the-art accelerators for Convolutional Neural Networks (CNNs) typically focus on accelerating only the convolutional layers, but do not prioritize the fully-connected layers much.
no code implementations • 16 Oct 2018 • Denise Ratasich, Faiq Khalid, Florian Geissler, Radu Grosu, Muhammad Shafique, Ezio Bartocci
Furthermore, this paper presents the main challenges in building a resilient IoT for CPS which is crucial in the era of smart CPS with enhanced connectivity (an excellent example of such a system is connected autonomous vehicles).